| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "eval_steps": 10, |
| "global_step": 528, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 2.116106641292572, |
| "epoch": 0.07585335018963338, |
| "grad_norm": 1.4921875, |
| "learning_rate": 5.6250000000000005e-05, |
| "loss": 2.914295959472656, |
| "mean_token_accuracy": 0.5410080701112747, |
| "num_tokens": 36823.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07585335018963338, |
| "eval_entropy": 2.552819073200226, |
| "eval_loss": 2.6676909923553467, |
| "eval_mean_token_accuracy": 0.5321294479072094, |
| "eval_num_tokens": 36823.0, |
| "eval_runtime": 14.7674, |
| "eval_samples_per_second": 0.542, |
| "eval_steps_per_second": 0.542, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.9473248382409414, |
| "epoch": 0.15170670037926676, |
| "grad_norm": 0.87890625, |
| "learning_rate": 9.999152908979117e-05, |
| "loss": 1.9090084075927733, |
| "mean_token_accuracy": 0.6584314892689387, |
| "num_tokens": 65881.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.15170670037926676, |
| "eval_entropy": 1.8724936991930008, |
| "eval_loss": 1.9479429721832275, |
| "eval_mean_token_accuracy": 0.6351580396294594, |
| "eval_num_tokens": 65881.0, |
| "eval_runtime": 14.8467, |
| "eval_samples_per_second": 0.539, |
| "eval_steps_per_second": 0.539, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.5991886417071024, |
| "epoch": 0.22756005056890014, |
| "grad_norm": 1.4765625, |
| "learning_rate": 9.984101496455829e-05, |
| "loss": 1.5578083038330077, |
| "mean_token_accuracy": 0.7192381203174592, |
| "num_tokens": 89977.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.22756005056890014, |
| "eval_entropy": 1.6338046044111252, |
| "eval_loss": 1.694503903388977, |
| "eval_mean_token_accuracy": 0.6637412160634995, |
| "eval_num_tokens": 89977.0, |
| "eval_runtime": 14.8298, |
| "eval_samples_per_second": 0.539, |
| "eval_steps_per_second": 0.539, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.6071883370478948, |
| "epoch": 0.3034134007585335, |
| "grad_norm": 0.71484375, |
| "learning_rate": 9.950291051311487e-05, |
| "loss": 1.6236091613769532, |
| "mean_token_accuracy": 0.6928597639004389, |
| "num_tokens": 122672.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.3034134007585335, |
| "eval_entropy": 1.5961390733718872, |
| "eval_loss": 1.5684512853622437, |
| "eval_mean_token_accuracy": 0.6787843257188797, |
| "eval_num_tokens": 122672.0, |
| "eval_runtime": 14.7973, |
| "eval_samples_per_second": 0.541, |
| "eval_steps_per_second": 0.541, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.3055346330006918, |
| "epoch": 0.37926675094816686, |
| "grad_norm": 0.9453125, |
| "learning_rate": 9.897848828427202e-05, |
| "loss": 1.2936326026916505, |
| "mean_token_accuracy": 0.7341216415166855, |
| "num_tokens": 152626.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.37926675094816686, |
| "eval_entropy": 1.4331321269273758, |
| "eval_loss": 1.410101294517517, |
| "eval_mean_token_accuracy": 0.7011745795607567, |
| "eval_num_tokens": 152626.0, |
| "eval_runtime": 14.7788, |
| "eval_samples_per_second": 0.541, |
| "eval_steps_per_second": 0.541, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.11328877111276, |
| "epoch": 0.45512010113780027, |
| "grad_norm": 0.82421875, |
| "learning_rate": 9.826972208488447e-05, |
| "loss": 1.0861340522766114, |
| "mean_token_accuracy": 0.766385022799174, |
| "num_tokens": 178156.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.45512010113780027, |
| "eval_entropy": 1.3111007660627365, |
| "eval_loss": 1.2872167825698853, |
| "eval_mean_token_accuracy": 0.7273842021822929, |
| "eval_num_tokens": 178156.0, |
| "eval_runtime": 14.7936, |
| "eval_samples_per_second": 0.541, |
| "eval_steps_per_second": 0.541, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.3175925850868224, |
| "epoch": 0.5309734513274337, |
| "grad_norm": 0.625, |
| "learning_rate": 9.737927955088705e-05, |
| "loss": 1.2941490173339845, |
| "mean_token_accuracy": 0.7372792253891627, |
| "num_tokens": 209487.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.5309734513274337, |
| "eval_entropy": 1.2998864650726318, |
| "eval_loss": 1.2285542488098145, |
| "eval_mean_token_accuracy": 0.7347995787858963, |
| "eval_num_tokens": 209487.0, |
| "eval_runtime": 14.8531, |
| "eval_samples_per_second": 0.539, |
| "eval_steps_per_second": 0.539, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.1506140291690827, |
| "epoch": 0.606826801517067, |
| "grad_norm": 0.828125, |
| "learning_rate": 9.631051210691558e-05, |
| "loss": 1.134031391143799, |
| "mean_token_accuracy": 0.760423094034195, |
| "num_tokens": 239555.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.606826801517067, |
| "eval_entropy": 1.2010595947504044, |
| "eval_loss": 1.1256182193756104, |
| "eval_mean_token_accuracy": 0.7571268677711487, |
| "eval_num_tokens": 239555.0, |
| "eval_runtime": 15.6324, |
| "eval_samples_per_second": 0.512, |
| "eval_steps_per_second": 0.512, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.9923018544912339, |
| "epoch": 0.6826801517067004, |
| "grad_norm": 1.0078125, |
| "learning_rate": 9.50674423523011e-05, |
| "loss": 0.9289534568786622, |
| "mean_token_accuracy": 0.7951417863368988, |
| "num_tokens": 265306.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.6826801517067004, |
| "eval_entropy": 1.0992150977253914, |
| "eval_loss": 1.0379621982574463, |
| "eval_mean_token_accuracy": 0.7777058333158493, |
| "eval_num_tokens": 265306.0, |
| "eval_runtime": 15.7361, |
| "eval_samples_per_second": 0.508, |
| "eval_steps_per_second": 0.508, |
| "step": 90 |
| }, |
| { |
| "entropy": 1.0375868437190852, |
| "epoch": 0.7585335018963337, |
| "grad_norm": 0.609375, |
| "learning_rate": 9.365474892091451e-05, |
| "loss": 1.0106287956237794, |
| "mean_token_accuracy": 0.7893585612376531, |
| "num_tokens": 292993.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.7585335018963337, |
| "eval_entropy": 1.072925515472889, |
| "eval_loss": 1.0008392333984375, |
| "eval_mean_token_accuracy": 0.7823155149817467, |
| "eval_num_tokens": 292993.0, |
| "eval_runtime": 15.602, |
| "eval_samples_per_second": 0.513, |
| "eval_steps_per_second": 0.513, |
| "step": 100 |
| }, |
| { |
| "entropy": 1.0960371459523837, |
| "epoch": 0.8343868520859671, |
| "grad_norm": 0.7890625, |
| "learning_rate": 9.207774887184493e-05, |
| "loss": 1.0759888648986817, |
| "mean_token_accuracy": 0.7768891970316569, |
| "num_tokens": 324472.0, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.8343868520859671, |
| "eval_entropy": 0.9983096048235893, |
| "eval_loss": 0.965083658695221, |
| "eval_mean_token_accuracy": 0.7886351868510246, |
| "eval_num_tokens": 324472.0, |
| "eval_runtime": 15.6552, |
| "eval_samples_per_second": 0.511, |
| "eval_steps_per_second": 0.511, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.8683194468418757, |
| "epoch": 0.9102402022756005, |
| "grad_norm": 0.859375, |
| "learning_rate": 9.034237767718997e-05, |
| "loss": 0.839997386932373, |
| "mean_token_accuracy": 0.8105442355076472, |
| "num_tokens": 350423.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.9102402022756005, |
| "eval_entropy": 0.9654994606971741, |
| "eval_loss": 0.9282829761505127, |
| "eval_mean_token_accuracy": 0.8008697852492332, |
| "eval_num_tokens": 350423.0, |
| "eval_runtime": 15.7206, |
| "eval_samples_per_second": 0.509, |
| "eval_steps_per_second": 0.509, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.8921634897589683, |
| "epoch": 0.9860935524652339, |
| "grad_norm": 0.66015625, |
| "learning_rate": 8.8455166882279e-05, |
| "loss": 0.8713577270507813, |
| "mean_token_accuracy": 0.805043849349022, |
| "num_tokens": 374888.0, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.9860935524652339, |
| "eval_entropy": 0.925379566848278, |
| "eval_loss": 0.9301751852035522, |
| "eval_mean_token_accuracy": 0.8013799041509628, |
| "eval_num_tokens": 374888.0, |
| "eval_runtime": 15.7302, |
| "eval_samples_per_second": 0.509, |
| "eval_steps_per_second": 0.509, |
| "step": 130 |
| }, |
| { |
| "entropy": 1.1222206217757726, |
| "epoch": 1.0606826801517066, |
| "grad_norm": 0.65625, |
| "learning_rate": 8.642321952241126e-05, |
| "loss": 1.0791142463684082, |
| "mean_token_accuracy": 0.779176946413719, |
| "num_tokens": 408924.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.0606826801517066, |
| "eval_entropy": 0.9091628380119801, |
| "eval_loss": 0.9220267534255981, |
| "eval_mean_token_accuracy": 0.8066961765289307, |
| "eval_num_tokens": 408924.0, |
| "eval_runtime": 15.6764, |
| "eval_samples_per_second": 0.51, |
| "eval_steps_per_second": 0.51, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.7742048308253289, |
| "epoch": 1.13653603034134, |
| "grad_norm": 0.74609375, |
| "learning_rate": 8.425418338863502e-05, |
| "loss": 0.7456035137176513, |
| "mean_token_accuracy": 0.8373923808336258, |
| "num_tokens": 437721.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.13653603034134, |
| "eval_entropy": 0.8886274918913841, |
| "eval_loss": 0.8979178071022034, |
| "eval_mean_token_accuracy": 0.8057176694273949, |
| "eval_num_tokens": 437721.0, |
| "eval_runtime": 15.6592, |
| "eval_samples_per_second": 0.511, |
| "eval_steps_per_second": 0.511, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.7018384074171384, |
| "epoch": 1.2123893805309733, |
| "grad_norm": 0.6484375, |
| "learning_rate": 8.195622224318879e-05, |
| "loss": 0.6607318878173828, |
| "mean_token_accuracy": 0.8447161267201105, |
| "num_tokens": 462626.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.2123893805309733, |
| "eval_entropy": 0.8706388957798481, |
| "eval_loss": 0.9000320434570312, |
| "eval_mean_token_accuracy": 0.8101153001189232, |
| "eval_num_tokens": 462626.0, |
| "eval_runtime": 15.6367, |
| "eval_samples_per_second": 0.512, |
| "eval_steps_per_second": 0.512, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.9497246752182643, |
| "epoch": 1.2882427307206068, |
| "grad_norm": 0.64453125, |
| "learning_rate": 7.953798509294372e-05, |
| "loss": 0.9422295570373536, |
| "mean_token_accuracy": 0.8010553220907847, |
| "num_tokens": 492653.0, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.2882427307206068, |
| "eval_entropy": 0.9001824222505093, |
| "eval_loss": 0.9093658924102783, |
| "eval_mean_token_accuracy": 0.8088075593113899, |
| "eval_num_tokens": 492653.0, |
| "eval_runtime": 15.6666, |
| "eval_samples_per_second": 0.511, |
| "eval_steps_per_second": 0.511, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.8425602326790492, |
| "epoch": 1.3640960809102403, |
| "grad_norm": 0.609375, |
| "learning_rate": 7.700857363649465e-05, |
| "loss": 0.8109879493713379, |
| "mean_token_accuracy": 0.8285688976446788, |
| "num_tokens": 523035.0, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.3640960809102403, |
| "eval_entropy": 0.8594749756157398, |
| "eval_loss": 0.8847923278808594, |
| "eval_mean_token_accuracy": 0.8098366558551788, |
| "eval_num_tokens": 523035.0, |
| "eval_runtime": 15.7401, |
| "eval_samples_per_second": 0.508, |
| "eval_steps_per_second": 0.508, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.7103817813098431, |
| "epoch": 1.4399494310998735, |
| "grad_norm": 0.625, |
| "learning_rate": 7.43775080074218e-05, |
| "loss": 0.6827019214630127, |
| "mean_token_accuracy": 0.8422260383764902, |
| "num_tokens": 548885.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.4399494310998735, |
| "eval_entropy": 0.8456171080470085, |
| "eval_loss": 0.8787115812301636, |
| "eval_mean_token_accuracy": 0.8125583752989769, |
| "eval_num_tokens": 548885.0, |
| "eval_runtime": 15.8473, |
| "eval_samples_per_second": 0.505, |
| "eval_steps_per_second": 0.505, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.9479823822776476, |
| "epoch": 1.515802781289507, |
| "grad_norm": 0.734375, |
| "learning_rate": 7.16546909426576e-05, |
| "loss": 0.949166202545166, |
| "mean_token_accuracy": 0.7941406567891439, |
| "num_tokens": 577576.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.515802781289507, |
| "eval_entropy": 0.8673977516591549, |
| "eval_loss": 0.8828094005584717, |
| "eval_mean_token_accuracy": 0.8098664358258247, |
| "eval_num_tokens": 577576.0, |
| "eval_runtime": 15.5839, |
| "eval_samples_per_second": 0.513, |
| "eval_steps_per_second": 0.513, |
| "step": 200 |
| }, |
| { |
| "entropy": 1.0111428305506707, |
| "epoch": 1.5916561314791404, |
| "grad_norm": 0.7265625, |
| "learning_rate": 6.885037051082091e-05, |
| "loss": 0.9710953712463379, |
| "mean_token_accuracy": 0.7993101666371027, |
| "num_tokens": 609960.0, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.5916561314791404, |
| "eval_entropy": 0.856759961694479, |
| "eval_loss": 0.8776929378509521, |
| "eval_mean_token_accuracy": 0.8108815997838974, |
| "eval_num_tokens": 609960.0, |
| "eval_runtime": 15.6851, |
| "eval_samples_per_second": 0.51, |
| "eval_steps_per_second": 0.51, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.6799834683537483, |
| "epoch": 1.6675094816687737, |
| "grad_norm": 0.7109375, |
| "learning_rate": 6.597510154080078e-05, |
| "loss": 0.6525429248809814, |
| "mean_token_accuracy": 0.8495604753494262, |
| "num_tokens": 636497.0, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.6675094816687737, |
| "eval_entropy": 0.8356063477694988, |
| "eval_loss": 0.8647487759590149, |
| "eval_mean_token_accuracy": 0.8143020421266556, |
| "eval_num_tokens": 636497.0, |
| "eval_runtime": 15.8097, |
| "eval_samples_per_second": 0.506, |
| "eval_steps_per_second": 0.506, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.8049038504560788, |
| "epoch": 1.7433628318584071, |
| "grad_norm": 0.76171875, |
| "learning_rate": 6.303970589576378e-05, |
| "loss": 0.7930676937103271, |
| "mean_token_accuracy": 0.8221095313628515, |
| "num_tokens": 662413.0, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.7433628318584071, |
| "eval_entropy": 0.8299686685204506, |
| "eval_loss": 0.8727775812149048, |
| "eval_mean_token_accuracy": 0.811675526201725, |
| "eval_num_tokens": 662413.0, |
| "eval_runtime": 15.6522, |
| "eval_samples_per_second": 0.511, |
| "eval_steps_per_second": 0.511, |
| "step": 230 |
| }, |
| { |
| "entropy": 1.0564268256227176, |
| "epoch": 1.8192161820480406, |
| "grad_norm": 0.578125, |
| "learning_rate": 6.00552317421046e-05, |
| "loss": 1.028653335571289, |
| "mean_token_accuracy": 0.790699835618337, |
| "num_tokens": 696264.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.8192161820480406, |
| "eval_entropy": 0.8743892759084702, |
| "eval_loss": 0.8777971267700195, |
| "eval_mean_token_accuracy": 0.8138757944107056, |
| "eval_num_tokens": 696264.0, |
| "eval_runtime": 15.7076, |
| "eval_samples_per_second": 0.509, |
| "eval_steps_per_second": 0.509, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.7534422516822815, |
| "epoch": 1.8950695322376738, |
| "grad_norm": 0.578125, |
| "learning_rate": 5.703291196664247e-05, |
| "loss": 0.7200803279876709, |
| "mean_token_accuracy": 0.841905082265536, |
| "num_tokens": 724679.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.8950695322376738, |
| "eval_entropy": 0.8260066509246826, |
| "eval_loss": 0.8556550741195679, |
| "eval_mean_token_accuracy": 0.8176052942872047, |
| "eval_num_tokens": 724679.0, |
| "eval_runtime": 15.5383, |
| "eval_samples_per_second": 0.515, |
| "eval_steps_per_second": 0.515, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.6556119327743848, |
| "epoch": 1.970922882427307, |
| "grad_norm": 0.90625, |
| "learning_rate": 5.39841218985715e-05, |
| "loss": 0.6228540897369385, |
| "mean_token_accuracy": 0.8531604041655858, |
| "num_tokens": 747645.0, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.970922882427307, |
| "eval_entropy": 0.7757505960762501, |
| "eval_loss": 0.8425352573394775, |
| "eval_mean_token_accuracy": 0.8199078440666199, |
| "eval_num_tokens": 747645.0, |
| "eval_runtime": 15.5078, |
| "eval_samples_per_second": 0.516, |
| "eval_steps_per_second": 0.516, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.9678725031977993, |
| "epoch": 2.04551201011378, |
| "grad_norm": 0.66015625, |
| "learning_rate": 5.0920336495290244e-05, |
| "loss": 0.9681121826171875, |
| "mean_token_accuracy": 0.7974661972563145, |
| "num_tokens": 782139.0, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.04551201011378, |
| "eval_entropy": 0.80567791685462, |
| "eval_loss": 0.8436932563781738, |
| "eval_mean_token_accuracy": 0.8152260556817055, |
| "eval_num_tokens": 782139.0, |
| "eval_runtime": 15.8016, |
| "eval_samples_per_second": 0.506, |
| "eval_steps_per_second": 0.506, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.8536191220084827, |
| "epoch": 2.1213653603034133, |
| "grad_norm": 0.5546875, |
| "learning_rate": 4.785308715325296e-05, |
| "loss": 0.7874747276306152, |
| "mean_token_accuracy": 0.8298017164071401, |
| "num_tokens": 813720.0, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.1213653603034133, |
| "eval_entropy": 0.7856072653084993, |
| "eval_loss": 0.846335232257843, |
| "eval_mean_token_accuracy": 0.819606214761734, |
| "eval_num_tokens": 813720.0, |
| "eval_runtime": 15.6923, |
| "eval_samples_per_second": 0.51, |
| "eval_steps_per_second": 0.51, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.6638347759842873, |
| "epoch": 2.197218710493047, |
| "grad_norm": 0.51953125, |
| "learning_rate": 4.479391830639727e-05, |
| "loss": 0.6242609977722168, |
| "mean_token_accuracy": 0.8523363530635834, |
| "num_tokens": 839868.0, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.197218710493047, |
| "eval_entropy": 0.7590906117111444, |
| "eval_loss": 0.8308372497558594, |
| "eval_mean_token_accuracy": 0.8229880109429359, |
| "eval_num_tokens": 839868.0, |
| "eval_runtime": 15.7361, |
| "eval_samples_per_second": 0.508, |
| "eval_steps_per_second": 0.508, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.7667473425467809, |
| "epoch": 2.27307206068268, |
| "grad_norm": 0.85546875, |
| "learning_rate": 4.1754343975501505e-05, |
| "loss": 0.7497875690460205, |
| "mean_token_accuracy": 0.8307713508605957, |
| "num_tokens": 868083.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.27307206068268, |
| "eval_entropy": 0.7566840350627899, |
| "eval_loss": 0.8286334276199341, |
| "eval_mean_token_accuracy": 0.8229979053139687, |
| "eval_num_tokens": 868083.0, |
| "eval_runtime": 15.5791, |
| "eval_samples_per_second": 0.514, |
| "eval_steps_per_second": 0.514, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.7993048436939716, |
| "epoch": 2.3489254108723134, |
| "grad_norm": 0.65234375, |
| "learning_rate": 3.8745804432010366e-05, |
| "loss": 0.742991590499878, |
| "mean_token_accuracy": 0.8361959497133891, |
| "num_tokens": 899190.0, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.3489254108723134, |
| "eval_entropy": 0.777919439598918, |
| "eval_loss": 0.8299288749694824, |
| "eval_mean_token_accuracy": 0.8192910104990005, |
| "eval_num_tokens": 899190.0, |
| "eval_runtime": 15.6799, |
| "eval_samples_per_second": 0.51, |
| "eval_steps_per_second": 0.51, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.6293849530319373, |
| "epoch": 2.4247787610619467, |
| "grad_norm": 0.8359375, |
| "learning_rate": 3.577962313943641e-05, |
| "loss": 0.581805419921875, |
| "mean_token_accuracy": 0.8652591675519943, |
| "num_tokens": 925260.0, |
| "step": 320 |
| }, |
| { |
| "epoch": 2.4247787610619467, |
| "eval_entropy": 0.7613311521708965, |
| "eval_loss": 0.8267746567726135, |
| "eval_mean_token_accuracy": 0.8222377151250839, |
| "eval_num_tokens": 925260.0, |
| "eval_runtime": 15.633, |
| "eval_samples_per_second": 0.512, |
| "eval_steps_per_second": 0.512, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.7733801044523716, |
| "epoch": 2.5006321112515804, |
| "grad_norm": 1.015625, |
| "learning_rate": 3.2866964134400294e-05, |
| "loss": 0.7303842067718506, |
| "mean_token_accuracy": 0.832006515065829, |
| "num_tokens": 950926.0, |
| "step": 330 |
| }, |
| { |
| "epoch": 2.5006321112515804, |
| "eval_entropy": 0.7464305143803358, |
| "eval_loss": 0.832525372505188, |
| "eval_mean_token_accuracy": 0.8221687376499176, |
| "eval_num_tokens": 950926.0, |
| "eval_runtime": 15.5554, |
| "eval_samples_per_second": 0.514, |
| "eval_steps_per_second": 0.514, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.8778012414773305, |
| "epoch": 2.5764854614412136, |
| "grad_norm": 0.6640625, |
| "learning_rate": 3.0018790007717667e-05, |
| "loss": 0.846740436553955, |
| "mean_token_accuracy": 0.8213575114806493, |
| "num_tokens": 984461.0, |
| "step": 340 |
| }, |
| { |
| "epoch": 2.5764854614412136, |
| "eval_entropy": 0.7818077709525824, |
| "eval_loss": 0.8265244960784912, |
| "eval_mean_token_accuracy": 0.8209226876497269, |
| "eval_num_tokens": 984461.0, |
| "eval_runtime": 15.6839, |
| "eval_samples_per_second": 0.51, |
| "eval_steps_per_second": 0.51, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.6396931484341621, |
| "epoch": 2.6523388116308473, |
| "grad_norm": 0.59765625, |
| "learning_rate": 2.7245820643682818e-05, |
| "loss": 0.5814118385314941, |
| "mean_token_accuracy": 0.8639077583948771, |
| "num_tokens": 1012244.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.6523388116308473, |
| "eval_entropy": 0.764773041009903, |
| "eval_loss": 0.8262049555778503, |
| "eval_mean_token_accuracy": 0.8203835636377335, |
| "eval_num_tokens": 1012244.0, |
| "eval_runtime": 15.7071, |
| "eval_samples_per_second": 0.509, |
| "eval_steps_per_second": 0.509, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.5754020652423303, |
| "epoch": 2.7281921618204805, |
| "grad_norm": 0.89453125, |
| "learning_rate": 2.4558492872844647e-05, |
| "loss": 0.5285086154937744, |
| "mean_token_accuracy": 0.8705056806405386, |
| "num_tokens": 1035096.0, |
| "step": 360 |
| }, |
| { |
| "epoch": 2.7281921618204805, |
| "eval_entropy": 0.7516557332128286, |
| "eval_loss": 0.828058123588562, |
| "eval_mean_token_accuracy": 0.8215344399213791, |
| "eval_num_tokens": 1035096.0, |
| "eval_runtime": 15.6975, |
| "eval_samples_per_second": 0.51, |
| "eval_steps_per_second": 0.51, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.8988088116049766, |
| "epoch": 2.8040455120101138, |
| "grad_norm": 0.7421875, |
| "learning_rate": 2.1966921190133207e-05, |
| "loss": 0.8750938415527344, |
| "mean_token_accuracy": 0.8111113180716832, |
| "num_tokens": 1070103.0, |
| "step": 370 |
| }, |
| { |
| "epoch": 2.8040455120101138, |
| "eval_entropy": 0.7701939102262259, |
| "eval_loss": 0.8284878730773926, |
| "eval_mean_token_accuracy": 0.8210262954235077, |
| "eval_num_tokens": 1070103.0, |
| "eval_runtime": 15.6584, |
| "eval_samples_per_second": 0.511, |
| "eval_steps_per_second": 0.511, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.611414231856664, |
| "epoch": 2.879898862199747, |
| "grad_norm": 0.46875, |
| "learning_rate": 1.948085968618452e-05, |
| "loss": 0.5515973567962646, |
| "mean_token_accuracy": 0.8679946422576904, |
| "num_tokens": 1098379.0, |
| "step": 380 |
| }, |
| { |
| "epoch": 2.879898862199747, |
| "eval_entropy": 0.7635957412421703, |
| "eval_loss": 0.8278843760490417, |
| "eval_mean_token_accuracy": 0.8201632648706436, |
| "eval_num_tokens": 1098379.0, |
| "eval_runtime": 15.5657, |
| "eval_samples_per_second": 0.514, |
| "eval_steps_per_second": 0.514, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.552935478836298, |
| "epoch": 2.9557522123893807, |
| "grad_norm": 0.60546875, |
| "learning_rate": 1.710966533514607e-05, |
| "loss": 0.5143342971801758, |
| "mean_token_accuracy": 0.8708932220935821, |
| "num_tokens": 1122556.0, |
| "step": 390 |
| }, |
| { |
| "epoch": 2.9557522123893807, |
| "eval_entropy": 0.7534672636538744, |
| "eval_loss": 0.8248686790466309, |
| "eval_mean_token_accuracy": 0.8210486173629761, |
| "eval_num_tokens": 1122556.0, |
| "eval_runtime": 15.7131, |
| "eval_samples_per_second": 0.509, |
| "eval_steps_per_second": 0.509, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.8567168667154798, |
| "epoch": 3.030341340075853, |
| "grad_norm": 0.7890625, |
| "learning_rate": 1.4862262777138747e-05, |
| "loss": 0.7992874622344971, |
| "mean_token_accuracy": 0.8247433890730648, |
| "num_tokens": 1154463.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.030341340075853, |
| "eval_entropy": 0.7517867274582386, |
| "eval_loss": 0.8263809680938721, |
| "eval_mean_token_accuracy": 0.8206864297389984, |
| "eval_num_tokens": 1154463.0, |
| "eval_runtime": 15.7327, |
| "eval_samples_per_second": 0.508, |
| "eval_steps_per_second": 0.508, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.7660068737963835, |
| "epoch": 3.106194690265487, |
| "grad_norm": 0.84765625, |
| "learning_rate": 1.2747110727926704e-05, |
| "loss": 0.6917660713195801, |
| "mean_token_accuracy": 0.8465665926535925, |
| "num_tokens": 1185696.0, |
| "step": 410 |
| }, |
| { |
| "epoch": 3.106194690265487, |
| "eval_entropy": 0.7465294413268566, |
| "eval_loss": 0.8320755362510681, |
| "eval_mean_token_accuracy": 0.821786604821682, |
| "eval_num_tokens": 1185696.0, |
| "eval_runtime": 15.6774, |
| "eval_samples_per_second": 0.51, |
| "eval_steps_per_second": 0.51, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.5761802410085995, |
| "epoch": 3.18204804045512, |
| "grad_norm": 0.6875, |
| "learning_rate": 1.077217014222125e-05, |
| "loss": 0.511052131652832, |
| "mean_token_accuracy": 0.8756706555684407, |
| "num_tokens": 1211766.0, |
| "step": 420 |
| }, |
| { |
| "epoch": 3.18204804045512, |
| "eval_entropy": 0.7379602193832397, |
| "eval_loss": 0.8376328349113464, |
| "eval_mean_token_accuracy": 0.8224689140915871, |
| "eval_num_tokens": 1211766.0, |
| "eval_runtime": 15.7026, |
| "eval_samples_per_second": 0.509, |
| "eval_steps_per_second": 0.509, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.6564679868519306, |
| "epoch": 3.2579013906447534, |
| "grad_norm": 0.94140625, |
| "learning_rate": 8.944874250444768e-06, |
| "loss": 0.5985485553741455, |
| "mean_token_accuracy": 0.8599840154250463, |
| "num_tokens": 1237420.0, |
| "step": 430 |
| }, |
| { |
| "epoch": 3.2579013906447534, |
| "eval_entropy": 0.7303919699043036, |
| "eval_loss": 0.8405498266220093, |
| "eval_mean_token_accuracy": 0.8218415826559067, |
| "eval_num_tokens": 1237420.0, |
| "eval_runtime": 15.6316, |
| "eval_samples_per_second": 0.512, |
| "eval_steps_per_second": 0.512, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.8293299699823061, |
| "epoch": 3.3337547408343866, |
| "grad_norm": 0.75390625, |
| "learning_rate": 7.2721005817299795e-06, |
| "loss": 0.7763681411743164, |
| "mean_token_accuracy": 0.8325149426857631, |
| "num_tokens": 1271456.0, |
| "step": 440 |
| }, |
| { |
| "epoch": 3.3337547408343866, |
| "eval_entropy": 0.7389508597552776, |
| "eval_loss": 0.8369100093841553, |
| "eval_mean_token_accuracy": 0.8209600448608398, |
| "eval_num_tokens": 1271456.0, |
| "eval_runtime": 15.8315, |
| "eval_samples_per_second": 0.505, |
| "eval_steps_per_second": 0.505, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.5659994448224703, |
| "epoch": 3.4096080910240203, |
| "grad_norm": 0.6015625, |
| "learning_rate": 5.7601450784531105e-06, |
| "loss": 0.5014583587646484, |
| "mean_token_accuracy": 0.8805189063151677, |
| "num_tokens": 1299758.0, |
| "step": 450 |
| }, |
| { |
| "epoch": 3.4096080910240203, |
| "eval_entropy": 0.7447542995214462, |
| "eval_loss": 0.8348008394241333, |
| "eval_mean_token_accuracy": 0.8216045647859573, |
| "eval_num_tokens": 1299758.0, |
| "eval_runtime": 15.6248, |
| "eval_samples_per_second": 0.512, |
| "eval_steps_per_second": 0.512, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.5874084360897541, |
| "epoch": 3.4854614412136535, |
| "grad_norm": 0.8517522215843201, |
| "learning_rate": 4.414698399728512e-06, |
| "loss": 0.5343384265899658, |
| "mean_token_accuracy": 0.8700998922189077, |
| "num_tokens": 23518.0, |
| "step": 460 |
| }, |
| { |
| "epoch": 3.4854614412136535, |
| "eval_entropy": 0.7440598104149103, |
| "eval_loss": 0.8360087871551514, |
| "eval_mean_token_accuracy": 0.8200278952717781, |
| "eval_num_tokens": 23518.0, |
| "eval_runtime": 13.5313, |
| "eval_samples_per_second": 0.591, |
| "eval_steps_per_second": 0.591, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.8708363252381484, |
| "epoch": 3.561314791403287, |
| "grad_norm": 0.7919224500656128, |
| "learning_rate": 3.24082450305262e-06, |
| "loss": 0.796872901916504, |
| "mean_token_accuracy": 0.8249703149000803, |
| "num_tokens": 58786.0, |
| "step": 470 |
| }, |
| { |
| "epoch": 3.561314791403287, |
| "eval_entropy": 0.7413963787257671, |
| "eval_loss": 0.836990475654602, |
| "eval_mean_token_accuracy": 0.8207731992006302, |
| "eval_num_tokens": 58786.0, |
| "eval_runtime": 13.624, |
| "eval_samples_per_second": 0.587, |
| "eval_steps_per_second": 0.587, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.5937250544627507, |
| "epoch": 3.6371681415929205, |
| "grad_norm": 0.7096187472343445, |
| "learning_rate": 2.2429415847114664e-06, |
| "loss": 0.5162258148193359, |
| "mean_token_accuracy": 0.8790442367394765, |
| "num_tokens": 86926.0, |
| "step": 480 |
| }, |
| { |
| "epoch": 3.6371681415929205, |
| "eval_entropy": 0.7403313536196947, |
| "eval_loss": 0.8373183012008667, |
| "eval_mean_token_accuracy": 0.8210151717066765, |
| "eval_num_tokens": 86926.0, |
| "eval_runtime": 13.6284, |
| "eval_samples_per_second": 0.587, |
| "eval_steps_per_second": 0.587, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.5804185174405575, |
| "epoch": 3.7130214917825537, |
| "grad_norm": 0.8440573215484619, |
| "learning_rate": 1.4248054506874108e-06, |
| "loss": 0.5123465538024903, |
| "mean_token_accuracy": 0.8726996392011642, |
| "num_tokens": 110886.0, |
| "step": 490 |
| }, |
| { |
| "epoch": 3.7130214917825537, |
| "eval_entropy": 0.7393731754273176, |
| "eval_loss": 0.8386462330818176, |
| "eval_mean_token_accuracy": 0.8204824104905128, |
| "eval_num_tokens": 110886.0, |
| "eval_runtime": 13.5845, |
| "eval_samples_per_second": 0.589, |
| "eval_steps_per_second": 0.589, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.7751463361084461, |
| "epoch": 3.788874841972187, |
| "grad_norm": 0.9721880555152893, |
| "learning_rate": 7.894953806535488e-07, |
| "loss": 0.7123836040496826, |
| "mean_token_accuracy": 0.8429674605528513, |
| "num_tokens": 143032.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 3.788874841972187, |
| "eval_entropy": 0.7396822646260262, |
| "eval_loss": 0.8389754295349121, |
| "eval_mean_token_accuracy": 0.8226290717720985, |
| "eval_num_tokens": 143032.0, |
| "eval_runtime": 13.6255, |
| "eval_samples_per_second": 0.587, |
| "eval_steps_per_second": 0.587, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.6546723035474619, |
| "epoch": 3.8647281921618206, |
| "grad_norm": 0.6209737658500671, |
| "learning_rate": 3.39402538260275e-07, |
| "loss": 0.5766997337341309, |
| "mean_token_accuracy": 0.8656552225351334, |
| "num_tokens": 171977.0, |
| "step": 510 |
| }, |
| { |
| "epoch": 3.8647281921618206, |
| "eval_entropy": 0.7403526566922665, |
| "eval_loss": 0.8384310007095337, |
| "eval_mean_token_accuracy": 0.8214001283049583, |
| "eval_num_tokens": 171977.0, |
| "eval_runtime": 13.5988, |
| "eval_samples_per_second": 0.588, |
| "eval_steps_per_second": 0.588, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.5892828449606895, |
| "epoch": 3.940581542351454, |
| "grad_norm": 0.5957433581352234, |
| "learning_rate": 7.62209713352613e-08, |
| "loss": 0.5226449012756348, |
| "mean_token_accuracy": 0.8693110903104146, |
| "num_tokens": 196534.0, |
| "step": 520 |
| }, |
| { |
| "epoch": 3.940581542351454, |
| "eval_entropy": 0.740116611123085, |
| "eval_loss": 0.8386836051940918, |
| "eval_mean_token_accuracy": 0.821216270327568, |
| "eval_num_tokens": 196534.0, |
| "eval_runtime": 13.6009, |
| "eval_samples_per_second": 0.588, |
| "eval_steps_per_second": 0.588, |
| "step": 520 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 528, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 10, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.608064609944781e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
